AI Agents

AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x

Self-hosted AI Agents Platform for AI Native companies. Claude Code, Codex, Gemini, OpenCode agents. Apache 2.0.

Open-source, desktop-grade AI agent that gets real work done — data analysis, slides, docs, video & web research. Built on OpenClaw; runs tools on your real desktop and takes commands from your phone via WeChat, Feishu, DingTalk & Telegram.

35 production-grade agentic AI architectures (Reflexion, LATS, GraphRAG, MemGPT, Voyager, BrowserAgent, ...) — a Python library and runnable textbook with multi-provider LLM support and a 17-task benchmark leaderboard.

Small plugins and mods that make your life (and Claude Code) better

A Codex skill for CTO, product manager, and engineer teams with task routing and completion follow-up.

Open-source Agent Operating System

An ops AI Agent that understands your infrastructure, finds the root cause, and fixes it — right from Slack, Telegram, Lark or DingTalk.

Ouroboros — self-creating AI agent. Born Feb 16, 2026.

Harness LLMs with Multi-Agent Programming

Open Instinct: an open-source Instinct. A personal agent you text on iMessage, with its own computer and a trusted network of other agents. Built on Pi, Inkbox, Maritime and Composio.

Token Efficiency For AI Agents

Squad: AI agent teams for any project

Creating realistic RL environments requires collaboration between researchers, engineers, and domain experts across many dimensions: artifacts, environments tools, dynamism of the environment, reproducibility, and more. There is no open source framework for building these environments effectively. Until now.

AI System Design - Learn how to design AI systems built on LLMs, RAG, and AI Agents step by step.

The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.

LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.

使用MCP，让你几乎所有的Agent访问QQ/微信/B站，甚至亲自下场水群和发消息！

The open-source, multi-agent alternative to Claude Tag. @ any agent, wherever work happens, they work alongside your team, learning as they go.

45+ tips for getting the most out of Claude Code, from basics to advanced - includes a custom status line script and Claude Code running itself in a container. Also includes the dx plugin: skills for everyday dev workflows.

A compilation of the best multi-agent papers

Hire Google's Antigravity CLI (agy) as a fast Gemini staffer for Claude Code and OpenAI Codex.

多Agent工作台，额度看得见、用完不断档、多个Agent相互协作，多任务并行开发。| Multi-agent workbench for Claude Code, Codex, Cursor and more. See your quota, keep working when it runs out, run tasks in parallel, let agents delegate.

Build effective agents using Model Context Protocol and simple workflow patterns

SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution

turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.

High-performance native SSH client in Rust, GPU-rendered with GPUI: host manager, terminal, WinSCP-style SFTP and port forwarding. Rust 编写、GPU 渲染的原生 SSH 客户端。

总结Prompt&LLM论文，开源数据&模型，AIGC应用

Multi-Agent Collaboration for Team and Friends

A local-first multi-agent app development platform, built on PenguinHarness

Claude Code plugin to see, review and iterate on your agent's work without leaving the terminal: show images, play videos, and run visual QA with Playwright recordings and before/after comparisons inside the Claude Code terminal. Works in any terminal that supports the kitty graphics protocol, fully cross-platform on macOS, Linux and Windows.

An open-source, code-first Java toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

Pack and deploy local AI agents for your team in minutes

Talk to Claude Code and Codex by voice, from your phone, on any of your machines. The open-source box agent for pitupitu.chat; your agents run in herdr.

One IDE for you and your AI team. A VS Code fork where Claude Code, Codex, Antigravity, and Muse Code work in parallel across multiple projects and features.

Replay your coding agent sessions as a map and a timeline

This repository is a collection of independent skills and tools for software development and automation. Each skill is a self-contained project with its own purpose, implementation, and documentation.

Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026.

Multi-Agent Harness for Production AI

Easily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM!

mu (μ): most of what a coding agent decides isn't code. mu hands 40 kinds of yes/no calls to a small model: fewer wasted tokens, fewer approvals on autopilot, fewer runs that stop halfway. Built on pi.

EMNLP 2026 Main Conference Paper: MASCOT: Towards Multi-Agent Socio-Collaborative Companion Systems (https://aclanthology.org/2026.emnlp-main.878/))

Reusable AI agent skills for software factories: explore ideas, write specs, implement, review, and run autonomous research. Works with Claude Code, Codex, and other skill-compatible agents.

Democratizing AI scientists with ToolUniverse

AI phone assistant | open-source

An AI-powered custom node for ComfyUI designed to enhance workflow automation and provide intelligent assistance

Run Hermes Agent and OpenClaw on the same WeChat account

Open-source multi-agent coding harness. Coordinate Claude Code, Codex, Cursor, Gemini CLI, Copilot, and more to split work, communicate, and hand off tasks at limits. Local-first, no account required. Works on macOS, Windows, and Linux.

Brigade — Your personal intelligence, built enterprise-grade

Koog is a JVM (Java and Kotlin) framework for building predictable, fault-tolerant and enterprise-ready AI agents across all platforms – from backend services to Android and iOS, JVM, and even in-browser environments. Koog is based on our AI products expertise and provides proven solutions for complex LLM and AI problems